Bargagna Enrico

Linkedin: https://www.linkedin.com/in/enrico-bargagna-7a3058269/

Contact mail: Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo.

Cycle: 41

Curriculum: Industrial Engineering

Title of the PhD Project:

Machine Learning-Driven Active Control for Microphonics Mitigation in SRF Cavities

Supervisor(s)

Paolo Neri

In collaboration with: Fermi National Accelerator Laboratory, Batavia, IL, USA

Abstract of the PhD project:

Microphonics-induced detuning represents a major limitation for superconducting radio-frequency (SRF) cavities, whose extremely high quality factors make them highly sensitive to micrometric mechanical vibrations. Conventional mitigation, based on increased RF power or passive isolation, offers limited effectiveness. This work proposes a machine learning-driven active control strategy that combines piezoelectric actuators, vibration and detuning detection, and a multiphysics digital twin of the cavity. The digital twin, developed through coupled mechanical-electromagnetic finite element simulations and calibrated with cryogenic measurements, provides a data set for training neural-network controllers capable of predicting and compensating detuning in real time. Transfer learning techniques are further explored to generalize the controller across different cavity geometries, reducing experimental costs. The proposed framework aims to achieve robust, scalable microphonics suppression and improving cavity stability. This approach has broad relevance for accelerators and cryogenic quantum technologies where precise frequency control is critical.

Experiences:

• Postgraduate Research Fellowship – University of Pisa (9 months)
• URA Visiting Scholars Fellowship – SQMS, Fermi National Accelerator Laboratory (2 months)
• Research Fellowship funded by the University of Pisa for thesis abroad – SQMS, Fermi National Accelerator Laboratory (6 months)

Teaching experience:

-

Publications

Articles

• Bargagna, E.; Delgado, J.; Wang, C.; Gonin, I.; Yakovlev, V.P.; Neri, P.; Passarelli, D.; Zorzetti, S. Design and Optimization of a Hybrid Design for Quantum Transduction. Sensors 2025, 25, 6365., DOI: 10.3390/s25206365.

Conferences

-

ORCID iD: 0009-0004-8954-0288

Scopus: https://www.scopus.com/authid/detail.uri?authorId=60162459700

Google Scholar: https://scholar.google.com/citations?user=aXGiOjMAAAAJ&hl=it

Research Gate: https://www.researchgate.net/profile/Enrico-Bargagna-2